SoylentNews is people
SoylentNews
The researchers, from the University of Cambridge, programmed a small fleet of miniature robotic cars to drive on a multi-lane track and observed how the traffic flow changed when one of the cars stopped.
When the cars were not driving cooperatively, any cars behind the stopped car had to stop or slow down and wait for a gap in the traffic, as would typically happen on a real road. A queue quickly formed behind the stopped car and overall traffic flow was slowed.
However, when the cars were communicating with each other and driving cooperatively, as soon as one car stopped in the inner lane, it sent a signal to all the other cars. Cars in the outer lane that were in immediate proximity of the stopped car slowed down slightly so that cars in the inner lane were able to quickly pass the stopped car without having to stop or slow down significantly.
Additionally, when a human-controlled driver was put on the 'road' with the autonomous cars and moved around the track in an aggressive manner, the other cars were able to give way to avoid the aggressive driver, improving safety.
The results, to be presented today at the International Conference on Robotics and Automation (ICRA) in Montréal, will be useful for studying how autonomous cars can communicate with each other, and with cars controlled by human drivers, on real roads in the future.
Sources:
- https://www.cam.ac.uk/research/news/driverless-cars-working-together-can-speed-up-traffic-by-35-percent
- https://www.bbc.com/news/uk-england-cambridgeshire-48326428
- https://www.autofutures.tv/2019/05/20/miniature-cars/
- https://techerati.com/news-hub/driverless-car-fleet-can-reduce-traffic-by-at-least-35-percent-research-suggests/
[Editors Comment: The submitter is linked professionally to the last of the listed sources. Additional source material, including the original paper from Cambridge University as primary source, is also listed.]
(Score: 2) by bob_super on Thursday May 23 2019, @05:21PM (2 children)
Car-sharing should reduce parking problems, because cars don't spend their whole day using a spot.
Car-sharing could reduce congestion, with the right app scheduling people to actually optimize vehicle capacity, including changing cars along the way. (buses, but car-sized and with dynamic routes). Hasn't happened yet, but it is theoretically possible.
This is about intelligent cars which are programmed to share the road capacity better than selfish humans.
Proper dialoging and yielding between cars can remove almost all traffic stops, and likely most of the jams.
My feedback: Thanks "researchers" for playing with robots, but the conclusion was known before you started, and you could have done it with a sim, like the professionals working on infrastructure do every day.
No, the "results" will NOT "be useful for studying how autonomous cars can communicate with each other, and with cars controlled by human drivers", because that was fucking obvious to start with, and the method doesn't scale like the existing sims.
Now, I'll go back to SupCom2, released almost a decade ago, in which hundreds of units of various sizes and speeds flow around each other and obstacles.
https://www.youtube.com/watch?v=bovlsENv1g4 [youtube.com]
(Score: 2) by Gaaark on Thursday May 23 2019, @09:01PM (1 child)
Ever played Total Annihilation, the forefather of SupCom?
Man, the units used to get in each others way ALL the fecking time.
Good game, though. I still play it.
--- Please remind me if I haven't been civil to you: I'm channeling MDC. ---Gaaark 2.0 ---
(Score: 2) by bob_super on Thursday May 23 2019, @09:20PM
Yes, but the problem with these old games is to find humans to play them with, because the AIs were pretty stupid at the time.
Supcom FA + LUA mods started having decent AIs that didn't result in one side getting crushed easily.
Put a good AI in TA, and you don't need any newer strategy game.
Put a good I (Organic or Artificial) in all cars, and 40 miles to L.A. could stop feeling worse than leaving to cross the Atlantic during peak hurricane season.